Medical system, method for processing medical image, and medical image processing apparatus

Abstract

A medical system includes a catheter that includes a sensor and insertable into a luminal organ and an image processing apparatus configured to: generate first cross-sectional images of the organ based on sensor signals output when the catheter is moved along the organ, select second images from the first images at predetermined intervals, input the second images to a machine learning model and acquire a type and region of an object in each second image, determine one second image as a reference, determine two or more first images generated before and after the reference, input said two or more first images to the model and acquire the type and region of the object in said two or more first images, and output information based on the type and region of the object acquired from each of the reference and said two or more first images.

What is claimed is: 
     
         1 . A medical system comprising:
 a catheter that includes a sensor and can be inserted into a luminal organ;   a display apparatus; and   an image processing apparatus configured to:
 generate a plurality of first cross-sectional images of the luminal organ based on signals that are output from the sensor when the catheter is being moved in a direction along the luminal organ therein, 
 select a plurality of second cross-sectional images from the first cross-sectional images at predetermined intervals, 
 input the second cross-sectional images to a machine learning model and acquire an output indicating a type and region of an object included in each of the second cross-sectional images, 
 determine one of the second cross-sectional images as a reference image based on the type and region of the object, 
 determine two or more of the first cross-sectional images generated before and after the reference image, 
 input said two or more of the first cross-sectional images to the machine learning model and acquire an output indicating the type and region of the object included in each of said two or more of the first cross-sectional images, and 
 cause the display apparatus to output information indicating the object based on the type and region of the object acquired from each of the reference image and said two or more of the first cross-sectional images. 
   
     
     
         2 . The medical system according to  claim 1 , wherein the image processing apparatus configured to:
 calculate a value indicating a characteristic of the object for each of the second cross-sectional images based on the type and region of the object, and   determine one of the second cross-sectional images as the reference image based on the value calculated for each of the second cross-sectional images.   
     
     
         3 . The medical system according to  claim 2 , wherein
 the luminal organ is a blood vessel,   the object is a plaque between an external elastic plate and a lumen of the blood vessel, and   the value indicating the characteristic of the object is a plaque burden.   
     
     
         4 . The medical system according to  claim 3 , wherein the image processing apparatus is configured to determine, as the reference image, one of the second cross-sectional images for which a maximum plaque burden is calculated. 
     
     
         5 . The medical system according to  claim 2 , wherein
 the image processing apparatus is configured to:
 determine, as a distal-side image, one of the second cross-sectional images of the luminal organ on a distal side of the luminal organ in the reference image, and 
 determine, as a proximal-side image, one of the second cross-sectional images of the luminal organ on a proximal side of the luminal organ in the reference image, and 
   said two or more of the first cross-sectional images are between the distal-side and proximal-side images.   
     
     
         6 . The medical system according to  claim 5 , wherein
 the value calculated for the distal-side image has a first minimum value among the values calculated for the second cross-sectional images of the luminal organ on the distal side of the luminal organ in the reference image, and   the value calculated for the proximal-side image has a second minimum value among the values calculated for the second cross-sectional images of the luminal organ on the proximal side of the luminal organ of the reference image.   
     
     
         7 . The medical system according to  claim 5 , wherein the image processing apparatus is configured to:
 determine a type of a stent to be inserted into the luminal organ based on the value calculated for each of the reference image and said two or more of the first cross-sectional images, and   cause the display device to display information regarding the determined type of the stent.   
     
     
         8 . The medical system according to  claim 7 , wherein the image processing apparatus is configured to:
 determine a landing zone of the stent in the luminal organ using the value calculated for each of the reference image and said two or more of the first cross-sectional images, and   determine a length of the stent based on the determined landing zone.   
     
     
         9 . The medical system according to  claim 7 , wherein the image processing apparatus is configured to:
 determine a diameter of a portion of the luminal organ between the luminal organs in the distal-side and proximal side images, and   determine a diameter of the stent based on the determined diameter of the portion of the luminal organ.   
     
     
         10 . The medical system according to  claim 1 , wherein
 the sensor of the catheter includes an ultrasound transmitter and receiver, and   the image processing apparatus is configured to generate an ultrasonic tomographic image of the luminal organ based on signals that are output from the sensor.   
     
     
         11 . A method for processing a medical image of a luminal organ, comprising:
 generating a plurality of first cross-sectional images of the luminal organ based on signals that are output from a sensor of a catheter when the catheter is inserted into the luminal organ and is being moved in a direction along the luminal organ;   selecting a plurality of second cross-sectional images from the first cross-sectional images at predetermined intervals;   inputting the second cross-sectional images to a machine learning model and acquiring an output indicating a type and region of an object included in each of the second cross-sectional images;   determining one of the second cross-sectional images as a reference image based on the type and region of the object;   determining two or more of the first cross-sectional images generated before and after the reference image;   inputting said two or more of the first cross-sectional images to the machine learning model and acquiring an output indicating the type and region of the object included in each of said two or more of the first cross-sectional images; and   outputting information indicating the object based on the type and region of the object acquired from each of the reference image and said two or more of the first cross-sectional images.   
     
     
         12 . The method according to  claim 11 , wherein determining one of the second cross-sectional images includes:
 calculating a value indicating a characteristic of the object for each of the second cross-sectional images based on the type and region of the object, and   determining one of the second cross-sectional images as the reference image based on the value calculated for each of the second cross-sectional images.   
     
     
         13 . The method according to  claim 12 , wherein
 the luminal organ is a blood vessel,   the object is a plaque between an external elastic plate and a lumen of the blood vessel, and   the value indicating the characteristic of the object is a plaque burden.   
     
     
         14 . The method according to  claim 13 , wherein the reference image is one of the second cross-sectional images for which a maximum plaque burden is calculated. 
     
     
         15 . The method according to  claim 12 , further comprising:
 determining, as a distal-side image, one of the second cross-sectional images of the luminal organ on a distal side of the luminal organ in the reference image; and   determining, as a proximal-side image, one of the second cross-sectional images of the luminal organ on a proximal side of the luminal organ in the reference image, and   said two or more of the first cross-sectional images are between the distal-side and proximal-side images.   
     
     
         16 . The method according to  claim 15 , wherein
 the value calculated for the distal-side image has a first minimum value among the values calculated for the second cross-sectional images of the luminal organ on the distal side of the luminal organ in the reference image, and   the value calculated for the proximal-side image has a second minimum value among the values calculated for the second cross-sectional images of the luminal organ on the proximal side of the luminal organ in the reference image.   
     
     
         17 . The method according to  claim 15 , further comprising:
 determining a type of a stent to be inserted into the luminal organ based on the value calculated for each of the reference image and said two or more of the first cross-sectional images; and   displaying information regarding the determined type of the stent.   
     
     
         18 . The method according to  claim 17 , wherein determining a type of a stent includes:
 determining a landing zone of the stent in the luminal organ using the value calculated for each of the reference image and said two or more of the first cross-sectional images, and   determining a length of the stent based on the determined landing zone.   
     
     
         19 . The method according to  claim 17 , wherein determining a type of a stent includes:
 determining a diameter of a portion of the luminal organ between the luminal organs in the distal-side and proximal side images, and   determining a diameter of the stent based on the determined diameter of the portion of the luminal organ.   
     
     
         20 . A medical image processing apparatus comprising:
 an interface circuit connectable to a display apparatus and a catheter that includes a sensor and can be inserted into a luminal organ; and   a processor configured to:
 generate a plurality of first cross-sectional images of the luminal organ based on signals that are output from the sensor when the catheter is being moved in a direction along the luminal organ therein, 
 select a plurality of second cross-sectional images from the first cross-sectional images at predetermined intervals, 
 input the second cross-sectional images to a machine learning model and acquire an output indicating a type and region of an object included in each of the second cross-sectional images, 
 determine one of the second cross-sectional images as a reference image based on the type and region of the object, 
 determine two or more of the first cross-sectional images generated before and after the reference image, 
 input said two or more of the first cross-sectional images to the machine learning model and acquire an output indicating the type and region of the object included in each of said two or more of the first cross-sectional images, and 
 cause the display apparatus to output information indicating the object based on the type and region of the object acquired from each of the reference image and said two or more of the first cross-sectional images.